UAV-based cargo transportation method, device and electronic equipment

Abstract

The embodiments of the present disclosure relate to the field of computer technology. The embodiments of the present disclosure disclose a method, device, and electronic device for drone-based cargo transportation. A specific implementation of the method includes: for initial task information, generating an initial transportation path group corresponding to the initial task information; generating an initial cargo distribution map based on the obtained initial transportation path group set; performing global path optimization on the initial cargo distribution map; generating a target transportation path set based on the optimized cargo distribution map; for the target transportation path, performing the following processing steps: according to at least one initial task information corresponding to the target transportation path, allocating a cargo drone corresponding to the target transportation path, and loading the cargo drone with cargo; in response to completion of loading, controlling the cargo drone corresponding to the target transportation path to transport the cargo along the target transportation path. This implementation effectively ensures the timeliness of cargo transportation of tobacco products.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and more particularly to a method, device, and electronic device for drone-based cargo transportation. Background Art

[0002] The transportation of tobacco products is one of the important links. Currently, transportation personnel are often required to deliver tobacco products to the corresponding delivery points (for example, sales points) in advance within a fixed time period. However, due to the influence of many environmental factors such as traffic congestion, it is difficult to effectively ensure the timeliness of tobacco product transportation. Summary of the Invention

[0003] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0004] Some embodiments of the present disclosure propose drone-based cargo transportation methods, devices, and electronic devices to solve one or more of the technical problems mentioned in the above background technology section.

[0005] In a first aspect, some embodiments of the present disclosure provide a method for transporting cargo based on drones, the method comprising: for each initial task information in an initial task information set, generating an initial transport path group corresponding to the initial task information according to the node position of the warehousing node and the node position of the node to be delivered included in the initial task information, wherein the initial task information in the initial task information set further comprises: cargo description information, the initial transport path group being at least one transport path corresponding to different transport path conditions; generating an initial cargo distribution graph based on the obtained initial transport path group set, wherein the initial cargo distribution graph is a graph with the warehousing node as the central node and the node to be delivered as the edge node. A star diagram of edge nodes; performing global path optimization on the above initial cargo distribution diagram to generate an optimized cargo distribution diagram; generating a set of target transportation paths based on the above optimized cargo distribution diagram, wherein the target transportation path is a transportation path with a storage node as the starting node and including at least one node to be delivered; for each target transportation path in the above target transportation path set, performing the following processing steps: allocating a cargo drone corresponding to the above target transportation path according to at least one initial task information corresponding to the target transportation path, and loading cargo onto the cargo drone; in response to completion of loading, controlling the cargo drone corresponding to the above target transportation path to transport cargo along the above target transportation path.

[0006] In a second aspect, some embodiments of the present disclosure provide a drone-based cargo transportation device, the device comprising: a first generating unit, configured to generate, for each initial task information in the initial task information set, an initial transportation path group corresponding to the initial task information according to the node position of the warehousing node and the node position of the node to be delivered included in the initial task information, wherein the initial task information in the initial task information set further comprises: cargo description information, the initial transportation path group being at least one transportation path corresponding to different transportation path conditions; a second generating unit, configured to generate an initial cargo distribution map based on the obtained initial transportation path group set, wherein the initial cargo distribution map is a star-shaped map with the warehousing node as the central node and the node to be delivered as the edge node. a global path optimization unit configured to perform global path optimization on the initial cargo distribution graph to generate an optimized cargo distribution graph; a third generation unit configured to generate a target transport path set based on the optimized cargo distribution graph, wherein the target transport path is a transport path starting from a storage node and including at least one node to be delivered; an execution unit configured to perform the following processing steps for each target transport path in the target transport path set: allocating a cargo drone corresponding to the target transport path according to at least one initial task information corresponding to the target transport path, and loading cargo onto the cargo drone; in response to completion of loading, controlling the cargo drone corresponding to the target transport path to transport cargo along the target transport path.

[0007] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0008] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0009] The above-described various embodiments of the present disclosure have the following beneficial effects: Through the drone-based cargo transportation methods of some embodiments of the present disclosure, the timeliness of tobacco product transportation is effectively guaranteed. Specifically, the reason for the inability to effectively guarantee timeliness is that it is difficult to effectively ensure timeliness due to the influence of numerous environmental factors such as traffic congestion. Based on this, the drone-based cargo transportation methods of some embodiments of the present disclosure first generate an initial transportation path group corresponding to each initial task information in the initial task information set based on the node location of the storage node and the node location of the node to be delivered included in the initial task information. The initial task information in the initial task information set also includes cargo description information, and the initial transportation path group comprises at least one transportation path corresponding to different transportation path conditions. This is used to plan at least one initial transportation path for transporting the cargo corresponding to the cargo description information. Secondly, based on the obtained initial transportation path group set, an initial cargo distribution graph is generated. The initial cargo distribution graph is a star-shaped graph with the storage node as the center node and the node to be delivered as the edge nodes. This generates a global path relationship between the initial transportation paths corresponding to the different initial task information. Next, the above-mentioned initial cargo distribution map is subjected to global path optimization to generate an optimized cargo distribution map. This reduces the number of transportation routes and improves distribution efficiency. Furthermore, based on the above-mentioned optimized cargo distribution map, a target transportation path set is generated, wherein the target transportation path is a transportation path starting from a storage node and including at least one node to be distributed. Finally, for each target transportation path in the above-mentioned target transportation path set, the following processing steps are performed: First, according to at least one initial task information corresponding to the target transportation path, a cargo drone corresponding to the above-mentioned target transportation path is allocated, and cargo is loaded onto the cargo drone. This realizes automated cargo loading. Second, in response to the completion of loading, the cargo drone corresponding to the above-mentioned target transportation path is controlled to transport cargo along the above-mentioned target transportation path. In this way, the timeliness of the transportation of tobacco products can be effectively guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0011] Figure 1 is a flow chart of some embodiments of the drone-based cargo transportation method according to the present disclosure;

[0012] Figure 2is a schematic diagram of an initial cargo distribution map of some embodiments of the drone-based cargo transportation method of the present disclosure;

[0013] Figure 3 is a schematic diagram of an optimized cargo distribution map of some embodiments of the drone-based cargo transportation method of the present disclosure;

[0014] Figure 4 is a top view of the body structure of a cargo drone according to some embodiments of the drone-based cargo transportation method disclosed herein;

[0015] Figure 5 is an oblique view of the body structure of a cargo drone according to some embodiments of the drone-based cargo transportation method disclosed herein;

[0016] Figure 6 is a side view of the body structure of a cargo drone according to some embodiments of the drone-based cargo transportation method disclosed herein;

[0017] Figure 7 is a schematic structural diagram of some embodiments of a drone-based cargo transport device according to the present disclosure;

[0018] Figure 8 It is a structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0021] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0022] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0025] refer to Figure 1 , shows a process 100 of some embodiments of the drone-based cargo transportation method according to the present disclosure. The drone-based cargo transportation method includes the following steps:

[0026] Step 101 : for each initial task information in the initial task information set, generate an initial transportation path group corresponding to the initial task information according to the node position of the storage node and the node position of the to-be-delivered node included in the initial task information.

[0027] In some embodiments, an execution entity (e.g., a computing device) of a drone-based cargo transportation method may generate an initial transportation route group corresponding to each initial task information in an initial task information set based on the node location of a storage node and the node location of a to-be-delivered node included in the initial task information. The initial task information may represent cargo transportation orders for which no cargo transportation has been completed. In practice, the execution entity may collect undelivered cargo transportation orders from the previous day, with a deadline of 24:00:00 daily, to form the initial task information set. A storage node represents a node where cargo is stored (e.g., a cargo storage node may be a tobacco storage warehouse or a tobacco transfer station). A to-be-delivered node represents a node where cargo is to be received. The initial task information in the initial task information set also includes cargo description information. In practice, the cargo description information may represent the cargo requirements of the cargo transportation order (e.g., the cargo description information may be cargo requirements for tobacco). Specifically, the cargo description information may include cargo model and cargo quantity required. The initial transportation route group comprises at least one transportation route corresponding to different transportation route conditions. In practice, the initial transport path is a direct path starting at the storage node and ending at the node to be delivered. In practice, the execution entity can determine the initial transport path group corresponding to the initial task information through path planning. Transport path conditions may include: a path priority condition and a time priority condition. The path priority condition specifies that the transport path between the storage node and the node to be delivered is the shortest. The time limit condition specifies that the transport time between the storage node and the node to be delivered is the shortest.

[0028] It should be noted that the computing device described above can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules, for example, to provide distributed services, or as a single software or software module. No specific limitations are given here.

[0029] In some optional implementations of some embodiments, the execution entity generates an initial transportation path group corresponding to the initial task information based on the node location of the storage node and the node location of the node to be delivered included in the initial task information, which may include the following steps:

[0030] The first step is to obtain a local road map.

[0031] The local route map is a regional map of the area where drone flight is not restricted and includes the node locations of the storage nodes and the node locations of the delivery nodes included in the initial mission information. In practice, the regional route map can be a three-dimensional route map that includes the drone's route and obstacles within the area. Specifically, by obtaining a local route map, the amount of route map-related data loaded can be greatly reduced compared to loading a full route map.

[0032] In the second step, the above local roadmap is spatially voxelized to generate a voxelized local roadmap.

[0033] In practice, the execution entity may spatially voxelize the local roadmap by octree sampling to generate a voxelized local roadmap, wherein the voxelized local roadmap includes M voxel cells, where M ≥ 8.

[0034] In the third step, voxel cell classification is performed on each of the above M voxel cells to generate a classification result.

[0035] The classification results include a first classification result and a second classification result. The first classification result indicates that the corresponding voxel cell contains an obstacle, while the second classification result indicates that the corresponding voxel cell does not contain an obstacle. In practice, the execution entity may first extract feature points from the voxel cell to obtain a feature point set. Specifically, when an obstacle is contained within a voxel cell, a set of feature points on the obstacle surface is obtained as the feature point set. The execution entity may then obtain plan views of the feature point set from the main perspective, left perspective, right perspective, bottom perspective, top perspective, and rear perspective, respectively, to obtain a plan view set. Since the obstacle is a three-dimensional structure, the feature points in the obtained feature point set are distributed within the space contained by the voxel cell, thereby obtaining plan views from various perspectives. Next, feature extraction is performed on the plan views in the plan view set using six parallel convolutional neural networks to obtain a view feature set. Furthermore, the view features in the view feature set are graph-joined to obtain stitched view features. Finally, the classification result is obtained using a binary classification model and the stitched view features. By converting the feature point set in the three-dimensional space into a plane image under various perspectives, the feature processing of one dimension can be reduced and the amount of data processing can be reduced.

[0036] In the fourth step, the voxel cells corresponding to the first classification result are filtered out from the M voxel cells, and the filtered voxel cells are used as the filtered voxel cells to obtain a filtered voxel cell set.

[0037] In the fifth step, taking the path length as the optimization target, the path traversal is performed according to the above filtered voxel cell set to obtain the initial transport path in the initial transport path group corresponding to the above initial task information.

[0038] In practice, the execution entity may first use an ant colony algorithm to traverse the filtered voxel cell set to obtain K transportation paths. Then, the shortest transportation path is selected from the K transportation paths as the initial transportation path in the initial transportation path group corresponding to the initial task information.

[0039] In the sixth step, taking the path duration as the optimization target, the path traversal is performed according to the filtered voxel cell set to obtain the initial transport path in the initial transport path group corresponding to the initial task information.

[0040] In practice, the execution entity can use an ant colony algorithm to traverse the filtered voxel cell set to obtain K transport paths. Then, the transport path with the shortest transit time is selected from the K transport paths and used as the initial transport path in the initial transport path group corresponding to the initial task information. Specifically, if a transport path contains an inflection point, it is considered that the drone may need to slow down. In this case, the number of inflection points in the transport path can be counted and combined with the path length to obtain a score for the transport path, which serves as the corresponding transit time.

[0041] Step 102: Generate an initial cargo distribution diagram based on the obtained initial transportation path group set.

[0042] In some embodiments, the execution entity may generate an initial cargo distribution map based on the obtained initial transportation path group set. The initial cargo distribution map is a star-shaped map with storage nodes as central nodes and nodes to be distributed as edge nodes. In practice, the execution entity may first update the storage nodes and nodes to be distributed into a blank map based on their respective locations. Next, the initial transportation path groups corresponding to the nodes to be distributed are updated into the blank map, thereby obtaining the initial cargo distribution map.

[0043] For example, see Figure 2 Figure 1 shows a schematic diagram of an initial cargo distribution graph, where the initial cargo distribution graph may include: a storage node, a node to be distributed A, a node to be distributed B, and a node to be distributed C. The dashed line represents the transportation path with the shortest transit time. The solid line represents the transportation path with the shortest transit time.

[0044] In some optional implementations of some embodiments, the execution entity may generate an initial cargo distribution map based on the obtained initial transportation path group set, which may include the following steps:

[0045] In the first step, an initial node matrix is ​​generated using the storage nodes and the nodes to be delivered included in the initial task information in the initial task information set.

[0046] The initial node matrix has a size of 1×N×2, where N represents the number of nodes to be delivered corresponding to the initial task information set. "1×N" represents one warehouse node and N nodes to be delivered. "N×2" represents N nodes to be delivered and the initial transportation paths (two initial transportation paths) corresponding to each node.

[0047] In the second step, the initial node matrix is ​​updated with the transportation path according to the initial transportation path group set to obtain the initial cargo distribution graph.

[0048] In practice, the execution entity can update the path information corresponding to each initial transportation path into the initial node matrix to obtain the initial cargo distribution map. The path information may include: path length and the set of coordinate points included in the path.

[0049] Step 103: Perform global path optimization on the initial cargo distribution graph to generate an optimized cargo distribution graph.

[0050] In some embodiments, the execution entity may perform global path optimization on the initial cargo distribution graph to generate an optimized cargo distribution graph.

[0051] For example, see further Figure 2 The schematic diagram of the initial cargo distribution graph is shown in FIG. Node B to be delivered is approximately located between the storage node and node C to be delivered. In this case, two separate deliveries are required for nodes B and C to be delivered, which reduces the overall delivery efficiency. In this case, a new transportation path can be constructed with the storage node as the starting node, node C to be delivered as the ending node, and node B to be delivered as the intermediate node. Specifically, the initial transportation path included in the initial cargo distribution graph can be optimized with the reduction of the overall path duration and overall path length as the optimization goal. For example, Figure 3 The schematic diagram of the optimized cargo distribution graph shown is shown, in which the initial transportation path between the warehousing node, the node to be distributed C and the node to be distributed B is optimized.

[0052] Step 104: Generate a target transportation route set based on the optimized cargo distribution graph.

[0053] In some embodiments, the execution entity may generate a set of target transportation routes based on the optimized cargo distribution map. A target transportation route is a transportation route starting at a warehouse node and including at least one node to be delivered. In practice, the execution entity may traverse the optimized cargo transportation map to obtain the set of target transportation routes.

[0054] For example, see further Figure 3 In the optimized cargo distribution diagram shown, the above-mentioned execution entity can use the solid line path between the warehousing node and the node to be delivered A as the target transportation path, and use the solid line path between the warehousing node, the node to be delivered B and the node to be delivered C as the target transportation path.

[0055] In some optional implementations of some embodiments, the execution entity generates a target transportation path set according to the optimized cargo distribution graph, which may include the following steps:

[0056] The first step is to determine the delivery model.

[0057] Delivery modes include: route-priority mode and time-priority mode. The route-priority mode prioritizes the length of the transport route. The time-priority mode prioritizes the duration of the route. In practice, the delivery mode can be determined based on the delivery requirements of the goods. For example, if the delivery needs to be completed in a short time, the time-priority mode can be selected. Alternatively, if the delivery needs to be completed with minimal resource consumption, the route-priority mode can be selected.

[0058] In the second step, in response to the distribution mode being the path priority mode, the following path generation steps are performed with the storage node included in the optimized cargo distribution graph as the starting node:

[0059] In the first sub-step, an initial transportation path that meets a first screening condition is selected from the optimized cargo distribution graph as a candidate transportation path.

[0060] The first screening condition is that the initial transport path is the initial transport path corresponding to the longest path length in the optimized cargo distribution graph.

[0061] In the second sub-step, the candidate transport paths are used as path constraints to traverse the optimized cargo distribution graph to obtain the target transport path set.

[0062] In practice, the path length of the screened target transport path is shorter than the path length of the candidate transport paths.

[0063] In the third step, in response to the delivery mode being the time-priority mode, the following path generation steps are performed, starting with the storage node included in the optimized cargo delivery graph:

[0064] In the first sub-step, an initial transportation path that meets the second screening condition is selected from the optimized cargo distribution graph as a candidate transportation path.

[0065] The second screening condition is that the initial transport path is the initial transport path corresponding to the longest path in the optimized cargo distribution diagram.

[0066] In the second sub-step, the candidate transport paths are used as path constraints to traverse the optimized cargo distribution graph to obtain the target transport path set.

[0067] In practice, the transit time of the selected target transport route is shorter than the transit time of the candidate transport routes.

[0068] Step 105: For each target transport path in the target transport path set, perform the following processing steps:

[0069] Step 1051: Allocate a cargo drone corresponding to the target transportation path according to at least one initial task information corresponding to the target transportation path, and load cargo onto the cargo drone.

[0070] In some embodiments, the execution entity may allocate a cargo drone corresponding to the target transport path and load cargo onto the cargo drone based on at least one initial task information corresponding to the target transport path.

[0071] In practice, when the target transport route is short, meaning a single drone can complete the transport, a single drone can be assigned. When the target transport route is long, meaning a single drone cannot complete the transport, multiple drones can be assigned, or a single drone can be used to transport multiple batches of cargo. The aforementioned execution entity can allocate a drone corresponding to the target transport route based on the drone's real-time flight range and carrying capacity. The cargo can then be loaded onto the drone.

[0072] For example, see Figure 4 The top view of the cargo drone's body structure is shown. Figure 5 The oblique view of the cargo drone's body structure is shown. Figure 6 The cargo drone is shown in a side view of its airframe structure, wherein the cargo drone comprises an airframe 1 and a power unit 2. Specifically, the airframe 1 of the cargo drone is a fixed-wing structure, and the cargo drone is powered by four power units 2.

[0073] In some optional implementations of some embodiments, the execution entity assigning a cargo drone corresponding to the target transportation route based on at least one initial task information corresponding to the target transportation route, and loading cargo onto the cargo drone, may include the following steps:

[0074] In the first step, according to the cargo description information included in the initial task information in at least one initial task information corresponding to the target transportation route, cargo is allocated by a self-propelled transport vehicle to transport the target cargo to a packaging area.

[0075] In practice, the execution entity may deploy goods using an Automated Guided Vehicle (AGV) to transport the target goods to the packaging area. Specifically, the AGV transports goods stored on shelves, corresponding to the target transportation route, and corresponding to the goods description information included in the initial task information in at least one initial task information, to the packaging area.

[0076] The second step is to control the packaging machine to package the target goods to obtain packaged goods.

[0077] In practice, the execution entity may package the target cargo using a packing machine to obtain packaged cargo. Specifically, the packaging box may include a magnetic fixing device on the outside, so that the target cargo can be fixed in the cargo drone cabin by electromagnetic means to prevent the cargo from rolling inside the drone and affecting the flight safety of the cargo drone.

[0078] The third step is to transport the packaged goods to a transfer area via a transport track in response to the completion of packaging.

[0079] A parking area is located above the transfer area, with a hydraulic lift installed between the transfer and parking areas. The parking area is also equipped with four return-to-nest markers. In practice, the transport track can be a circular transport track between the transfer and packaging areas to transport packaged goods to the transfer area. The return-to-nest markers are used to guide the cargo drone for precise takeoff and landing.

[0080] Step 4: In response to the transport being completed, execute the following target steps:

[0081] In the first sub-step, the cargo drone corresponding to the target transport path is controlled to move to the transfer area according to the four return calibration points.

[0082] In practice, the cargo drone can first capture the image below. Then, it can locate the location of the homing calibration point in the image below. Then, it can adjust the position of the cargo drone based on the location so that the cargo drone can park within the parking area.

[0083] In the second sub-step, in response to the cargo drone corresponding to the target transport path moving to the transfer area and stopping, the cargo drone corresponding to the target transport path is controlled to open the hatch.

[0084] In practice, the above-mentioned execution entity can initiate a hatch opening command to the cargo drone to control the cargo drone to open the hatch.

[0085] The third sub-step is to control the hydraulic lift to load the packaged cargo into the cargo drone cabin corresponding to the above-mentioned target transportation path in response to the hatch opening.

[0086] The cargo drone secures the encapsulated cargo via an electromagnetic device within its cabin. In practice, when powered, the electromagnetic device can magnetically secure the cargo in place within the cabin. Specifically, to reduce power consumption, the electromagnetic device can be de-energized during stable flight. When the drone is in severe weather, such as strong winds or heavy rain, the electromagnetic device can be energized to secure the cargo and prevent it from swaying within the cabin, potentially affecting the drone's flight stability and, consequently, flight safety.

[0087] The fourth sub-step is to close the hatch of the cargo drone corresponding to the target transport path in response to the completion of loading.

[0088] Step 1052: In response to the loading being completed, the cargo drone corresponding to the target transport path is controlled to transport the cargo along the target transport path.

[0089] In some embodiments, the execution entity may control the cargo drone corresponding to the target transport route in response to completion of loading, and transport the cargo along the target transport route.

[0090] In some optional implementations of some embodiments, after controlling the cargo drone corresponding to the target transportation route to transport the cargo along the target transportation route in response to completion of loading, the method further includes:

[0091] The first step is to obtain real-time drone status information and real-time environment information.

[0092] The real-time drone status information represents the drone status of the cargo drone corresponding to the target transport route during flight. The real-time environmental information represents the surrounding environment of the cargo drone corresponding to the target transport route during flight. The real-time drone status information includes drone acceleration, drone speed, drone altitude above the ground, and an obstacle list. The obstacle information in the obstacle list includes obstacle type and obstacle distance, and the real-time environmental information includes wind speed, humidity, and visibility. Specifically, the real-time drone status information and real-time environmental information can be collected by sensors within the cargo drone.

[0093] In the second step, the target transport path is updated based on the real-time UAV status information and the real-time environmental information to generate a locally updated transport path.

[0094] The partially updated transport route is shared with nearby cargo drones corresponding to the target transport route through a path sharing method. In practice, subtle environmental changes, such as weather variations, may occur. If a drone flies entirely along the target transport route, this could be dangerous. Therefore, adjustments are made based on real-time drone status information and environmental information to ensure the cargo drone's flight safety. Furthermore, the cargo drone synchronizes the partially updated transport route with nearby cargo drones via Wi-Fi, achieving a "one-machine update, multiple-machine simultaneous use" effect through sharing and reducing duplicate data processing. Alternatively, path sharing can be achieved by transmitting the partially updated transport route to the aforementioned execution entity, which then distributes it to nearby cargo drones.

[0095] Optionally, updating the target transport path according to the real-time drone status information and the real-time environment information to generate a partially updated transport path may include the following steps:

[0096] In the first sub-step, a drone state information extraction model is used to extract features from the drone state information to obtain drone state features.

[0097] The drone shape information extraction model includes: a drone acceleration feature extraction model, a drone velocity feature extraction model, a drone height above the ground feature extraction model, and an obstacle information feature extraction model. In practice, the drone acceleration feature extraction model, the drone velocity feature extraction model, the drone height above the ground feature extraction model, and the obstacle information feature extraction model all have the same model structure, using a recurrent neural network model.

[0098] In the second sub-step, a real-time environment information extraction model is used to extract features from the real-time environment information to obtain real-time environment features.

[0099] The above-mentioned real-time environmental feature extraction model includes: a wind speed information feature extraction model, a humidity information feature extraction model and a visibility information feature extraction model.

[0100] In practice, the wind speed information feature extraction model, humidity information feature extraction model, and visibility information feature extraction model all use the CNN (Convolutional Neural Network) + LSTM (Long-Short Term Memory) model.

[0101] The third sub-step is to generate the above-mentioned locally updated transportation path based on the above-mentioned UAV state characteristics, the above-mentioned real-time environment characteristics and the path prediction model.

[0102] In practice, the route prediction model consists of a feature fusion layer and a prediction head. Specifically, the feature fusion model fuses drone state features with real-time environmental features. The prediction head uses a five-layer serially connected convolutional neural network to predict the route and obtain a locally updated transport route.

[0103] The third step is to adjust the flight route of the cargo drone corresponding to the above target transport path based on the above partially updated transport path.

[0104] In practice, the execution entity can update the portion of the target transport route corresponding to the partially updated transport route to the partially updated transport route, thereby adjusting the cargo drone's flight path. The aforementioned drone state information extraction model and real-time environmental information extraction model can optimize the cargo drone's flight path and improve flight safety based on both the drone's flight state and the environment in which it is located.

[0105] The above-described various embodiments of the present disclosure have the following beneficial effects: Through the drone-based cargo transportation methods of some embodiments of the present disclosure, the timeliness of tobacco product transportation is effectively guaranteed. Specifically, the reason for the inability to effectively guarantee timeliness is that it is difficult to effectively ensure timeliness due to the influence of numerous environmental factors such as traffic congestion. Based on this, the drone-based cargo transportation methods of some embodiments of the present disclosure first generate an initial transportation path group corresponding to each initial task information in the initial task information set based on the node location of the storage node and the node location of the node to be delivered included in the initial task information. The initial task information in the initial task information set also includes cargo description information, and the initial transportation path group comprises at least one transportation path corresponding to different transportation path conditions. This is used to plan at least one initial transportation path for transporting the cargo corresponding to the cargo description information. Secondly, based on the obtained initial transportation path group set, an initial cargo distribution graph is generated. The initial cargo distribution graph is a star-shaped graph with the storage node as the center node and the node to be delivered as the edge nodes. This generates a global path relationship between the initial transportation paths corresponding to the different initial task information. Next, the above-mentioned initial cargo distribution map is subjected to global path optimization to generate an optimized cargo distribution map. This reduces the number of transportation routes and improves distribution efficiency. Furthermore, based on the above-mentioned optimized cargo distribution map, a target transportation path set is generated, wherein the target transportation path is a transportation path starting from a storage node and including at least one node to be distributed. Finally, for each target transportation path in the above-mentioned target transportation path set, the following processing steps are performed: First, according to at least one initial task information corresponding to the target transportation path, a cargo drone corresponding to the above-mentioned target transportation path is allocated, and cargo is loaded onto the cargo drone. This realizes automated cargo loading. Second, in response to the completion of loading, the cargo drone corresponding to the above-mentioned target transportation path is controlled to transport cargo along the above-mentioned target transportation path. In this way, the timeliness of the transportation of tobacco products can be effectively guaranteed.

[0106] Further references Figure 7 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a cargo transportation device based on a drone. These device embodiments are similar to Figure 1Corresponding to the method embodiments shown, the drone-based cargo transportation device can be specifically applied to various electronic devices.

[0107] like Figure 7 As shown, some embodiments of the UAV-based cargo transportation device 700 include: a first generation unit 701, a second generation unit 702, a global path optimization unit 703, a third generation unit 704 and an execution unit 705. The first generation unit 701 is configured to generate, for each initial task information in the initial task information set, an initial transportation path group corresponding to the initial task information according to the node position of the storage node and the node position of the node to be delivered included in the initial task information, wherein the initial task information in the initial task information set further includes: cargo description information, and the initial transportation path group is at least one transportation path corresponding to different transportation path conditions; the second generation unit 702 is configured to generate an initial cargo distribution graph based on the obtained initial transportation path group set, wherein the initial cargo distribution graph is a star graph with the storage node as the central node and the node to be delivered as the edge node; the global path optimization unit 703 ... transportation path group for each initial task information in the initial task information set, wherein the initial task information in the initial task information set further includes: cargo description information, and the initial transportation path group is at least one transportation path corresponding to different transportation path conditions; the second generation unit 702 is configured to generate an initial cargo distribution graph based on the obtained initial transportation path group set, wherein the initial cargo distribution graph is a star graph with the storage node as the central node and the node to be delivered as the edge node; the global path optimization unit 703 is configured to generate an initial transportation path group for each initial task information in the initial task information set, wherein the initial transportation path group is a star graph with the storage node as the central node and the node to be delivered as the edge node. The above-mentioned initial cargo distribution map is subjected to global path optimization to generate an optimized cargo distribution map; the third generation unit 704 is configured to generate a target transportation path set according to the above-mentioned optimized cargo distribution map, wherein the target transportation path is a transportation path with a warehousing node as the starting node and including at least one node to be distributed; the execution unit 705 is configured to perform the following processing steps for each target transportation path in the above-mentioned target transportation path set: according to at least one initial task information corresponding to the target transportation path, a freight drone corresponding to the above-mentioned target transportation path is allocated, and the freight drone is loaded with cargo; in response to the completion of loading, the freight drone corresponding to the above-mentioned target transportation path is controlled to transport cargo along the above-mentioned target transportation path.

[0108] It is understood that the units described in the drone-based cargo transport device 700 are similar to those in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the drone-based cargo transport device 700 and the units included therein, and will not be repeated here.

[0109] Reference below Figure 8 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 800 suitable for implementing some embodiments of the present disclosure. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0110] like Figure 8As shown, electronic device 800 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 801, which can perform various appropriate actions and processes based on programs stored in a read-only memory 802 or programs loaded from a storage device 808 into a random access memory 803. The random access memory 803 also stores various programs and data required for the operation of electronic device 800. The processing device 801, the read-only memory 802, and the random access memory 803 are connected to each other via a bus 804. An input / output interface 805 is also connected to the bus 804.

[0111] Typically, the following devices may be connected to the input / output interface 805: an input device 806 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 808 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 809. The communication device 809 may allow the electronic device 800 to communicate with other devices wirelessly or by wire to exchange data. Figure 8 The electronic device 800 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 8 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0112] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via the communication device 809, or installed from the storage device 808, or installed from the read-only memory 802. When the computer program is executed by the processing device 801, the above-mentioned functions defined in the method of some embodiments of the present disclosure are performed.

[0113] It should be noted that the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable storage media may include, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. Furthermore, in some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. This propagated data signal may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wire, optical cable, RF (radio frequency), or any suitable combination thereof.

[0114] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0115] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: for each initial task information in the initial task information set, according to the node position of the warehousing node and the node position of the node to be delivered included in the above-mentioned initial task information, an initial transportation path group corresponding to the above-mentioned initial task information is generated, wherein the initial task information in the above-mentioned initial task information set also includes: cargo description information, the initial transportation path group is at least one transportation path corresponding to different transportation path conditions; based on the obtained initial transportation path group set, an initial cargo distribution map is generated, wherein the above-mentioned initial cargo distribution map is a map with the warehousing node as the central node and the node position of the node to be delivered as the central node. A star graph with distribution nodes as edge nodes; performing global path optimization on the above initial cargo distribution graph to generate an optimized cargo distribution graph; generating a set of target transport paths based on the above optimized cargo distribution graph, wherein the target transport path is a transport path with a storage node as the starting node and including at least one node to be distributed; for each target transport path in the above target transport path set, performing the following processing steps: allocating a cargo drone corresponding to the above target transport path based on at least one initial task information corresponding to the target transport path, and loading cargo onto the cargo drone; in response to completion of loading, controlling the cargo drone corresponding to the above target transport path to transport cargo along the above target transport path.

[0116] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0117] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0118] The units described in some embodiments of the present disclosure may be implemented in software or in hardware. The units described may also be provided in a processor. For example, they may be described as follows: a processor comprising a first generation unit, a second generation unit, a global path optimization unit, a third generation unit, and an execution unit. The names of these units do not, in some cases, constitute limitations on the units themselves. For example, the global path optimization unit may also be described as a "unit that performs global path optimization on the above-mentioned initial cargo distribution diagram to generate an optimized cargo distribution diagram."

[0119] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0120] The above descriptions are merely some preferred embodiments of the present disclosure and illustrate the underlying technical principles. Those skilled in the art should understand that the scope of the invention encompassed by the embodiments of the present disclosure is not limited to technical solutions formed by specific combinations of the aforementioned technical features. It also encompasses other technical solutions formed by any combination of the aforementioned technical features or their equivalents, without departing from the aforementioned inventive concept. For example, a technical solution formed by replacing the aforementioned features with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for transporting cargo using drones, comprising: For each initial task information in the initial task information set, an initial transportation path group corresponding to the initial task information is generated based on the node position of the warehousing node and the node position of the node to be delivered included in the initial task information, wherein the initial task information in the initial task information set further includes: cargo description information, the initial transportation path group is at least one transportation path corresponding to different transportation path conditions, and the transportation path conditions include: a path priority condition and a time priority condition, the path priority condition indicates that the path length of the transportation path between the warehousing node and the node to be delivered is the shortest, and the time priority condition indicates that the transportation time between the warehousing node and the node to be delivered is the shortest; Generate an initial cargo distribution graph based on the obtained initial transportation path group set, wherein the initial cargo distribution graph is a star graph with the storage node as the central node and the nodes to be distributed as the edge nodes; Performing global path optimization on the initial cargo distribution graph to generate an optimized cargo distribution graph; Generate a target transportation path set based on the optimized cargo distribution graph, wherein the target transportation path is a transportation path starting from a storage node and including at least one node to be distributed; For each target transport path in the target transport path set, the following processing steps are performed: Allocating a cargo drone corresponding to the target transport path according to at least one initial task information corresponding to the target transport path, and loading the cargo drone with cargo; In response to the completion of loading, the cargo drone corresponding to the target transportation path is controlled to transport the cargo along the target transportation path, wherein: The generating of an initial transportation path group corresponding to the initial task information according to the node position of the storage node and the node position of the to-be-delivered node included in the initial task information includes: Obtaining a local route map, wherein the local route map is an area map that does not restrict the flight of the drone and includes the node locations of the storage nodes and the node locations of the nodes to be delivered included in the initial task information; Performing spatial voxelization on the local roadmap to generate a voxelized local roadmap, wherein the voxelized local roadmap includes: M voxel units, where M is greater than or equal to 8; Performing voxel cell classification on each of the M voxel cells to generate a classification result, wherein the classification result includes: a first classification result and a second classification result, the first classification result indicating that the corresponding voxel cell contains an obstacle, and the second classification result indicating that the corresponding voxel cell does not contain an obstacle; Filtering out voxel cells whose corresponding classification results are the second classification results from the M voxel cells as filtered voxel cells, thereby obtaining a filtered voxel cell set; Taking path length as an optimization goal, performing path traversal according to the filtered voxel cell set to obtain an initial transport path in an initial transport path group corresponding to the initial task information; Taking the path duration as the optimization target, the path traversal is performed according to the filtered voxel cell set to obtain the initial transport path in the initial transport path group corresponding to the initial task information. The generating of the initial cargo distribution graph based on the obtained initial transport path group set includes: Generate an initial node matrix using the warehouse nodes and the nodes to be delivered included in the initial task information in the initial task information set, wherein the matrix size of the initial node matrix is ​​1×N×2, where N represents the number of nodes to be delivered corresponding to the initial task information set; The initial node matrix is ​​updated with transportation paths according to the initial transportation path group set to obtain the initial cargo distribution graph.

2. The method according to claim 1, wherein After controlling the cargo drone corresponding to the target transportation path to transport the cargo along the target transportation path in response to loading completion, the method further includes: Acquire real-time drone status information and real-time environmental information, wherein the real-time drone status information represents the drone status of the cargo drone corresponding to the target transport path during flight, and the real-time environmental information represents the surrounding environment of the cargo drone corresponding to the target transport path during flight, the real-time drone status information includes: drone acceleration, drone speed, drone height above the ground, and an obstacle information list, the obstacle information in the obstacle information list includes: obstacle type and obstacle distance value, and the real-time environmental information includes: wind speed information, humidity information, and visibility information; updating the target transport path according to the real-time UAV status information and the real-time environmental information to generate a partially updated transport path, wherein the partially updated transport path is shared with adjacent cargo UAVs corresponding to the target transport path through a path sharing method; According to the partially updated transport path, the flight route of the cargo UAV corresponding to the target transport path is adjusted.

3. A cargo transport device based on a drone, comprising: The first generating unit is configured to generate, for each initial task information in the initial task information set, an initial transportation path group corresponding to the initial task information based on the node position of the warehousing node and the node position of the node to be delivered included in the initial task information, wherein the initial task information in the initial task information set further includes: cargo description information, the initial transportation path group is at least one transportation path corresponding to different transportation path conditions, the transportation path conditions include: a path priority condition and a time priority condition, the path priority condition indicates that the path length of the transportation path between the warehousing node and the node to be delivered is the shortest, and the time limit condition indicates that the transportation time between the warehousing node and the node to be delivered is the shortest; The second generating unit is configured to generate an initial cargo distribution graph based on the obtained initial transportation path group set, wherein the initial cargo distribution graph is a star graph with the storage node as the central node and the nodes to be distributed as the edge nodes; a global path optimization unit configured to perform global path optimization on the initial cargo distribution graph to generate an optimized cargo distribution graph; A third generating unit is configured to generate a set of target transportation paths based on the optimized cargo distribution graph, wherein the target transportation path is a transportation path starting from a storage node and including at least one node to be delivered; The execution unit is configured to perform the following processing steps for each target transport path in the target transport path set: assigning a cargo drone corresponding to the target transport path according to at least one initial task information corresponding to the target transport path, and loading cargo onto the cargo drone; in response to loading completion, controlling the cargo drone corresponding to the target transport path to transport cargo along the target transport path, wherein: The generating of an initial transportation path group corresponding to the initial task information according to the node position of the storage node and the node position of the to-be-delivered node included in the initial task information includes: Obtaining a local route map, wherein the local route map is an area map that does not restrict the flight of the drone and includes the node locations of the storage nodes and the node locations of the nodes to be delivered included in the initial task information; Performing spatial voxelization on the local roadmap to generate a voxelized local roadmap, wherein the voxelized local roadmap includes: M voxel units, where M is greater than or equal to 8; Performing voxel cell classification on each of the M voxel cells to generate a classification result, wherein the classification result includes: a first classification result and a second classification result, the first classification result indicating that the corresponding voxel cell contains an obstacle, and the second classification result indicating that the corresponding voxel cell does not contain an obstacle; Filtering out voxel cells whose corresponding classification results are the second classification results from the M voxel cells as filtered voxel cells, thereby obtaining a filtered voxel cell set; Taking path length as an optimization goal, performing path traversal according to the filtered voxel cell set to obtain an initial transport path in an initial transport path group corresponding to the initial task information; Taking the path duration as the optimization target, the path traversal is performed according to the filtered voxel cell set to obtain the initial transport path in the initial transport path group corresponding to the initial task information. The generating of the initial cargo distribution graph based on the obtained initial transport path group set includes: Generate an initial node matrix using the warehouse nodes and the nodes to be delivered included in the initial task information in the initial task information set, wherein the matrix size of the initial node matrix is ​​1×N×2, where N represents the number of nodes to be delivered corresponding to the initial task information set; The initial node matrix is ​​updated with transportation paths according to the initial transportation path group set to obtain the initial cargo distribution graph.

4. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 2.

5. A computer-readable medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.

Images